watch-pr

watch-pr is a skill for Claude Code from justincampbell/gh-watch. It costs 48 tokens per session (1,136 once invoked), scanned A, original, MIT.

A command that watches a GitHub pull request for automated checks, reviews, comments, merge conflicts, and final states. A pull request is a proposed code change waiting for review and merging.

In plain words
What is it for?
Use it to wait for CI results, a submitted review, a merge, a closure, or a change in the merge queue for a pull request.
Why use it?
It removes the need to keep refreshing GitHub while waiting for tests, reviews, or a merge decision.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the gh-watch plugin — 4 skills shipped together

Good fit Use it to wait for CI results, a submitted review, a merge, a closure, or a change in the merge queue for a pull request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/justincampbell/gh-watch/watch-pr
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add justincampbell/gh-watch --skill watch-pr
Clone the repo
git clone --depth 1 https://github.com/justincampbell/gh-watch

Made for: Claude Code.

Or install gh-watch, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for watch-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/justincampbell/gh-watch/watch-pr/github.svg)](https://agentmods.dev/skills/justincampbell/gh-watch/watch-pr)
Your own site
<a href="https://agentmods.dev/skills/justincampbell/gh-watch/watch-pr"><img src="https://agentmods.dev/badge/skills/justincampbell/gh-watch/watch-pr/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for watch-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/justincampbell/gh-watch/watch-pr"><img src="https://agentmods.dev/badge/skills/justincampbell/gh-watch/watch-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,136 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01136
Opus 5.5 $0.00019 $0.00454
Sonnet 5.5 $0.00010 $0.00227
Haiku 4.5 $0.00005 $0.00114

Measured 1mo ago against content hash 8e2a16c6784f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

watch-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/watch-pr/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watch a Pull Request

Monitor a pull request for state changes using the gh watch CLI extension. It polls GitHub and emits one JSON event per line to stdout, which makes it a natural fit for the Monitor tool — each event arrives in the conversation as a notification.

Prerequisites

Check if the extension is installed:

gh watch --help

If not installed:

gh extension install justincampbell/gh-watch

Usage

Run with the Monitor tool (not Bash with run_in_background). Each stdout line — starting with initial-state — is delivered as a notification, so you react to events as they land instead of polling an output file.

Wait for CI to finish, then exit — use a bounded timeout_ms and let --exit-on end the watch:

  • command: gh watch pr $ARGUMENTS --exit-on ci-passed,ci-failed,pr-merged,pr-closed
  • description: PR $ARGUMENTS CI status
  • persistent: false
  • timeout_ms: 1800000 (30 min — raise for slow CI)

Wait for a code review:

  • command: gh watch pr $ARGUMENTS --exit-on review-submitted

Wait until a queued PR resolves (merges or gets kicked out of the merge queue):

  • command: gh watch pr $ARGUMENTS --exit-on pr-merged,merge-queue-removed

Watch the PR for the rest of the session (CI + reviews + comments + merge state):

  • command: gh watch pr $ARGUMENTS
  • description: PR $ARGUMENTS state changes
  • persistent: true (no timeout — stop with TaskStop or end of session)

If no PR number is provided, the PR for the current branch is detected automatically. To watch a PR in another repo, prefix the command with GH_REPO=owner/repo (the pr subcommand takes a number, not a URL).

Flags

Flag Description Default
--interval <duration> Polling interval 60s
--exit Exit after any state change false
--exit-on <events> Exit after specific event types (comma-separated)

Event types

Event Description
initial-state Snapshot of PR state at the moment watching started (always emitted first)
ci-passed All CI checks passed
ci-failed CI failed (at least one check failed)
review-submitted A review was submitted
comment-added A new comment was posted
merge-conflict-changed Mergeable state changed
merge-queue-entered PR was added to the merge queue
merge-queue-status-changed Merge queue entry changed state (e.g. AWAITING_CHECKS → UNMERGEABLE)
merge-queue-removed PR left the merge queue without merging (e.g. kicked out on failure)
pr-merged PR was merged (terminal — always exits)
pr-closed PR was closed (terminal — always exits)

Read the full file on GitHub · 101 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 101 lines · 48 tokens per session scan A 8e2a16c6784f

Subscribe to this mod's changes

watch-pr is a skill published in the GitHub repository justincampbell/gh-watch (4 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,136 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.